search

GuyTevet / motion-diffusion-model

The official PyTorch implementation of the paper "Human Motion Diffusion Model"
MIT License
3.11k stars 334 forks source link

Not enough values to unpack (expected 2, got 0) #219

Open zwxiao1 opened 1 month ago

zwxiao1 commented 1 month ago

i am runnig "python -m sample.edit --model_path ./save/humanml_trans_enc_512/model000200000.pt --edit_mode upper_body --text_condition "A person throws a ball" then it get /content/motion-diffusion-model/diffusion/nn.py:151: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead. def forward(ctx, run_function, length, args): /content/motion-diffusion-model/diffusion/nn.py:161: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead. def backward(ctx, output_grads): Loading dataset... Reading ././dataset/humanml_opt.txt Loading dataset t2m ... 100% 4384/4384 [00:00<00:00, 146714.13it/s] Traceback (most recent call last): File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/usr/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/content/motion-diffusion-model/sample/edit.py", line 199, in main() File "/content/motion-diffusion-model/sample/edit.py", line 45, in main data = get_dataset_loader(name=args.dataset, File "/content/motion-diffusion-model/data_loaders/get_data.py", line 44, in get_dataset_loader dataset = get_dataset(name, num_frames, split, hml_mode) File "/content/motion-diffusion-model/data_loaders/get_data.py", line 37, in get_dataset dataset = DATA(split=split, num_frames=num_frames, mode=hml_mode) File "/content/motion-diffusion-model/data_loaders/humanml/data/dataset.py", line 764, in init self.t2m_dataset = Text2MotionDatasetV2(self.opt, self.mean, self.std, self.split_file, self.w_vectorizer) File "/content/motion-diffusion-model/data_loaders/humanml/data/dataset.py", line 275, in init name_list, length_list = zip(*sorted(zip(new_name_list, length_list), key=lambda x: x[1])) ValueError: not enough values to unpack (expected 2, got 0)

i have read the issues #90 but it not works

Gabriel001217 commented 1 week ago

@zwxiao1 Have you unziped the texts.zip in ./dataset/HumanML3D/ ? I had the same problem and when I did that the problem was solved.